Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    زا
    -0.06
    Reflection
    -0.06
     Playstation
    -0.06
    BALL
    -0.06
    ังไม
    -0.06
    -income
    -0.06
    νονται
    -0.06
    etik
    -0.05
    Seek
    -0.05
    (graph
    -0.05
    POSITIVE LOGITS
     обнаруж
    0.08
     treaties
    0.07
    иплом
    0.06
     inspire
    0.06
    ßer
    0.06
     lead
    0.06
    ，但
    0.06
    "]->
    0.06
     actions
    0.06
     illum
    0.06
    Act Density 0.023%

    No Known Activations